how can I access the weight??? and bias??

Question

atefeh gh 2014-8-26

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/152431-how-can-i-access-the-weight-and-bias

回答： Greg Heath 2014-8-30

hi I am a beginer. after design a perceptron neural network how can I access the weight??? and bias?? I dont mean sim(net). Kindly guide me. Thanks,

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Greg Heath 2014-8-30

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/152431-how-can-i-access-the-weight-and-bias#answer_150243

在 MATLAB Online 中打开

If you you normalize your inputs and targets using maxmin or mapstd, the function for the normalized variables is

 yn = B2 + LW*tansig(IW*xn+B1);
 Hope this helps.

Thank you for formally accepting my answer

Greg

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

Answer 2

Greg Heath 2014-8-28

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/152431-how-can-i-access-the-weight-and-bias#answer_150062

在 MATLAB Online 中打开

 clear all, clc 
[x,t] = simplefit_dataset;
 net   = fitnet;
 rng(0)
 net   = train(net,x,t);
 IW    = net.IW{1,1} 
 b1    = net.b{1} 
 LW    = net.LW{2,1}
 b2    = net.b{2}
whos IW b1 LW b2

Hope this helps.

Thank you for formally accepting my answer

Greg

2 个评论
显示无隐藏无

atefeh gh 2014-8-28

thanks so if I want to write a function for this how can write this?? here I think we have one feature but w and b are 10, so how can Relating them to each other and make a function for it ?? Suppose that my feature is X.

atefeh gh 2014-8-28